{"ID":2889440,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.22289","arxiv_id":"2507.22289","title":"Intent Recognition and Out-of-Scope Detection using LLMs in Multi-party Conversations","abstract":"Intent recognition is a fundamental component in task-oriented dialogue systems (TODS). Determining user intents and detecting whether an intent is Out-of-Scope (OOS) is crucial for TODS to provide reliable responses. However, traditional TODS require large amount of annotated data. In this work we propose a hybrid approach to combine BERT and LLMs in zero and few-shot settings to recognize intents and detect OOS utterances. Our approach leverages LLMs generalization power and BERT's computational efficiency in such scenarios. We evaluate our method on multi-party conversation corpora and observe that sharing information from BERT outputs to LLMs leads to system performance improvement.","short_abstract":"Intent recognition is a fundamental component in task-oriented dialogue systems (TODS). Determining user intents and detecting whether an intent is Out-of-Scope (OOS) is crucial for TODS to provide reliable responses. However, traditional TODS require large amount of annotated data. In this work we propose a hybrid app...","url_abs":"https://arxiv.org/abs/2507.22289","url_pdf":"https://arxiv.org/pdf/2507.22289v1","authors":"[\"Galo Castillo-López\",\"Gaël de Chalendar\",\"Nasredine Semmar\"]","published":"2025-07-29T23:48:41Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.LG\"]","methods":"[\"Large Language Model\"]","has_code":false}